Parkinson's disease detection using modulation components in speech signals

Parkinson's disease (PD) is the second most prevalent neurodegenerative disorder after Alzheimer's. This disorder affects around 2% of elderly population. In Colombia, the prevalence of Parkinson's disease is around 172 cases per 100.000 inhabitants. Furthermore, around 89% of people diagnosed with PD also suffer from speech disorders. This has motivated many advances in speech signal processing for PD patients which allows to perform assisted diagnosis and also monitor the progression of the disease. In this paper, we propose to use slow varying information from speech signals, also known as modulation components, and combine it with an approach to effectively reduce the number of features to be used in a classification system. The proposed approach achieves around 90% accuracy, outperforming the classical mel-frequency cepstral coefficients (MFCC) approach. Results show that information in slow varying components is highly discriminative to support assisted diagnosis for PD.